Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    German words

    oai_token-act-pair · gpt-3.5-turbo

    references to cultural or artistic themes, particularly in a German context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyes
    -0.86
    Mex
    -0.86
    Jones
    -0.75
    Snake
    -0.75
    taboola
    -0.74
    Kansas
    -0.73
    OIL
    -0.72
    RAY
    -0.71
     Guerrero
    -0.71
    Mexico
    -0.71
    POSITIVE LOGITS
     Ãľ
    0.93
     alle
    0.91
     Volks
    0.84
     die
    0.83
    heit
    0.76
     euro
    0.75
     organis
    0.75
     bes
    0.74
     von
    0.74
     Europa
    0.73
    Act Density 0.160%

    No Known Activations